The Grasp Loop Signature: A Topological Representation for Manipulation Planning with Ropes and Cables

TL;DR

This paper proposes the G-L - Signature topology, which categorizes the topology of these grasp loops and shows how it can be used to guide planning, and performs experiments in simulation on two DOO manipulation tasks to show that using the G-L - Signature is faster and more successful than methods that rely on local geometry or additional finite-horizon planning.

Abstract

Robotic manipulation of deformable, one-dimensional objects (DOOs) like ropes or cables has important potential applications in manufacturing, agriculture, and surgery. In such environments, the task may involve threading through or avoiding becoming tangled with objects like racks or frames. Grasping with multiple grippers can create closed loops between the robot and DOO, and If an obstacle lies within this loop, it may be impossible to reach the goal. However, prior work has only considered the topology of the DOO in isolation, ignoring the arms that are manipulating it. Searching over possible grasps to accomplish the task without considering such topological information is very inefficient, as many grasps will not lead to progress on the task due to topological constraints. Therefore, we propose a grasp loop signature which categorizes the topology of these grasp loops and show how it can be used to guide planning. We perform experiments in simulation on two DOO manipulation tasks to show that using the signature is faster and succeeds more often than methods that rely on local geometry or finite-horizon planning. Finally, we demonstrate using the signature in the real world to manipulate a cable in a scene with obstacles using a dual-arm robot.

Figures (5)

• Figure 1: Annotated image of our real world cable threading setup. The red dashed line shows a grasp loop $\tau_1$ that is linked with the skeleton $\mathit{S}_1$. The blue grasp loop is not linked with $\mathit{S}_1$. This distinction is captured by the proposed ${\mathcal{G}_L}$-signature and is used in planning.
• Figure 2: (A) Illustration of the h-signature for a loop representing the robot and DOO (red/blue) and a loop representing an obstacle (black). (B) Two examples of the h-signature for a skeleton with two obstacle loops $S_1$ and $S_2$.
• Figure 3: The process of constructing the ${\mathcal{G}_L}$-signature. (C) There are 2 grasp loops and 3 object loops, so the ${\mathcal{G}_L}$-signature is a set with two elements, and each element is a vector of 3 non-negative integers.
• Figure 4: Example scenes and their ${\mathcal{G}_L}$ values. The dashed blue and red lines are grasp loops, and the solid black lines are obstacle loops. (B.3) The blue grasp loop is omitted from the signature, as described in Section \ref{['sec:defGL']}. The purple sphere shows the goal region.
• Figure 5: Additional examples where the ${\mathcal{G}_L}$-signature may be useful. (A) Drones lifting a large object can be treated similarly to a multi-armed robot. (B) Dual-arm grasping of large rigid objects can result in distinct signatures.